Most humans take a year to learn their first steps, and they are notoriously clumsy. [Hartvik Line] taught a robotic cat to walk [YouTube link] in less time, but this cat had a couple advantages over a pre-toddler. The first advantage was that it had four legs, while the second came from a machine learning technique called genetic algorithms that surpassed human fine-tuning in two hours. That’s a pretty good benchmark.
The robot itself is an impressive piece inspired by robots at EPFL, a research institute in Switzerland. All that Swiss engineering is not easy for one person to program, much less a student, but that is exactly what happened. “Nixie,” as she is called, is a part of a master thesis for [Hartvik] at the University of Stavanger in Norway. Machine learning efficiency outstripped human meddling very quickly, and it can even relearn to walk if the chassis is damaged.
This image was generated with a landscape model using a dataset containing covers of Japanese poetry books.
The work is centered around the use of Generative Adversarial Networks, or GANs. [Helena] describes using a GAN to create artworks as a sort of game. An apprentice attempts to create new works in the style of their established master, while a critic attempts to determine whether the artworks are created by the master or the apprentice. As the apprentice improves, the critic must become more discerning; as the critic becomes more discerning, the apprentice must improve further. It is through this mechanism that the model improves itself.
[Helena] has spent time experimenting with CycleGAN in the artistic realm after first using it in a work project, and has primarily trained it on her own original artworks to create new pieces with wild and exciting results. She shares several tips on how best to work with the technology, around the necessary computing and storage requirements, as well as ways to step out of the box to create more diverse outputs.
Scientists don’t know exactly what fast radio bursts (FRBs) are. What they do know is that they come from a long way away. In fact, one that occurs regularly comes from a galaxy 3 billion light years away. They could form from neutron stars or they could be extraterrestrials phoning home. The other thing is — thanks to machine learning — we now know about a lot more of them. You can see a video from Berkeley, below. and find more technical information, raw data, and [Danielle Futselaar’s] killer project graphic seen above from at their site.
The first FRB came to the attention of [Duncan Lorimer] and [David Narkevic] in 2007 while sifting through data from 2001. These broadband bursts are hard to identify since they last a matter of milliseconds. Researchers at Berkeley trained software using previously known FRBs. They then gave the software 5 hours of recordings of activity from one part of the sky and found 72 previously unknown FRBs.
Nvidia is back at it again with another awesome demo of applied machine learning: artificially transforming standard video into slow motion – they’re so good at showing off what AI can do that anyone would think they were trying to sell hardware for it.
Though most modern phones and cameras have an option to record in slow motion, it often comes at the expense of resolution, and always at the expense of storage space. For really high frame rates you’ll need a specialist camera, and you often don’t know that you should be filming in slow motion until after an event has occurred. Wouldn’t it be nice if we could just convert standard video to slow motion after it was recorded?
That’s just what Nvidia has done, all nicely documented in a paper. At its heart, the algorithm must take two frames, and artificially create one or more frames in between. This is not a manual algorithm that interpolates frames, this is a fully fledged deep-learning system. The Convolutional Neural Network (CNN) was trained on over a thousand videos – roughly 300k individual frames.
Since none of the parameters of the CNN are time-dependent, it’s possible to generate as many intermediate frames as required, something which sets this solution apart from previous approaches. In some of the shots in their demo video, 30fps video is converted to 240fps; this requires the creation of 7 additional frames for every pair of consecutive frames.
The video after the break is seriously impressive, though if you look carefully you can see the odd imperfection, like the hockey player’s skate or dancer’s arm. Deep learning is as much an art as a science, and if you understood all of the research paper then you’re doing pretty darn well. For the rest of us, get up to speed by wrapping your head around neural networks, and trying out the simplest Tensorflow example.
Once you step into the world of controls, you quickly realize that controlling even simple systems isn’t as easy as applying voltage to a servo. Before you start working on your own bipedal robot or scratch-built drone, though, you might want to get some practice with this intricate field of engineering. A classic problem in this area is the inverted pendulum, and [Philip] has created a great model of this which helps illustrate the basics of controls, with some AI mixed in.
Called the ZIPY, the project is a “Cart Pole” design that uses a movable cart on a trolley to balance a pendulum above. The pendulum is attached at one point to the cart. By moving the cart back and forth, the pendulum can be kept in a vertical position. The control uses the OpenAI Gym toolkit which is a way to easily use reinforcement learning algorithms in your own projects. With some Python, some 3D printed parts, and the toolkit, [Philip] was able to get his project to successfully balance the pendulum on the cart.
Of course, the OpenAI Gym toolkit is useful for many more projects where you might want some sort of machine learning to help out. If you want to play around with machine learning without having to build anything, though, you can also explore it in your browser.
Readers of a certain vintage will remember the glee of building your own levels for DOOM. There was something magical about carefully crafting a level and then dialing up your friends for a death match session on the new map. Now computers scientists are getting in on that fun in a new way. Researchers from Politecnico di Milano are using artificial intelligence to create new levels for the classic DOOM shooter (PDF whitepaper).
While procedural level generation has been around for decades, recent advances in machine learning to generate game content (usually levels) are different because they don’t use a human-defined algorithm. Instead, they generate new content by using existing, human-generated levels as a model. In effect they learn from what great game designers have already done and apply those lesson to new level generation. The screenshot shown above is an example of an AI generated level and the gameplay can be seen in the video below.
The idea of an AI generating levels is simple in concept but difficult in execution. The researchers used Generative Adversarial Networks (GANs) to analyze existing DOOM maps and then generate new maps similar to the originals. GANs are a type of neural network which learns from training data and then generates similar data. They considered two types of GANs when generating new levels: one that just used the appearance of the training maps, and another that used both the appearance and metrics such as the number of rooms, perimeter length, etc. If you’d like a better understanding of GANs, [Steven Dufresne] covered it in his guide to the evolving world of neural networks.
While both networks used in this project produce good levels, the one that included other metrics resulted in higher quality levels. However, while the AI-generated levels appeared similar at a high level to human-generated levels, many of the little details that humans tend to include were omitted. This is partially due to a lack of good metrics to describe levels and AI-generated data.
Example DOOM maps generated by AI. Each row is one map, and each image is one aspect of the map (floor, height, things, and walls, from left to right)
We can only guess that these researcher’s next step is to use similar techniques to create an entire game (levels, characters, and music) via AI. After all, how hard can it be?? Joking aside, we would love to see you take this concept and run with it. We’re dying to play through some gnarly levels whipped up by the AI from Hackaday readers!
Last year, Google released an artificial intelligence kit aimed at makers, with two different flavors: Vision to recognize people and objections, and Voice to create a smart speaker. Now, Google is back with a new version to make it even easier to get started.
The main difference in this year’s (v1.1) kits is that they include some basic hardware, such as a Raspberry Pi and an SD card. While this might not be very useful to most Hackaday readers, who probably have a spare Pi (or 5) lying around, this is invaluable for novice makers or the educational market. These audiences now have access to an all-in-one solution to build projects and learn more about artificial intelligence.
We’ve previously seen toys,phones, and intercoms get upgrades with an AIY kit, but would love to see more! [Mike Rigsby] has used one in his robot dog project to detect when people are smiling. These updated kits are available at Target (Voice, Vision). If the kit is too expensive, our own [Inderpreet Singh] can show you how to build your own.
